AI Agents
AI agents are LLM-powered systems that don't just answer — they plan steps, call tools and drive a task to completion: writing code, searching the web, booking, analyzing. 2026 became the year of agents, from coding agents to autonomous researchers. This page gathers all our coverage of agentic AI: launches, protocols (MCP, A2A), reliability and real-world use.
FMR Method Reduces RL Agent Alignment Errors by 98% in Imitation Learning
Researchers introduced Feedback Manipulation Regularization — a single-pass alignment method for RL agents that reduces value constraint vio
Self-Evolving LLM Agents: Compiling SOPs into Tools Reduces Latency by 42%
Researchers showed how pre-compiling standard SOP steps into verified tools reduces agent latency by 42% and error rates by 53% in real prod
Meta released Muse Spark 1.1 — multimodal agent with 1 million token context
NVIDIA Nemotron 3 Ultra sets an accuracy record among open models in LangChain test
Former GitHub CEO launched a distributed Git network for the era of agentic coding
GitLost vulnerability on GitHub: AI agents leak data from private repositories
Anthropic launched Claude Cowork on mobile devices and in the browser
Anthropic has opened access to the Claude Cowork collaboration platform for iOS, Android, and browsers — it was previously available only in
Anthropic brings Claude Cowork to smartphones — tasks keep running without a laptop
Anthropic has made Claude Cowork mobile: tasks keep running in the background even after the laptop is closed — the company is betting on ma